© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109377
    Prev
    Next
    INDEX
    Explanations

    class property names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bogus
    0.53
     ***",
    0.46
    さと
    0.46
     wellknown
    0.44
    ="",
    0.44
     updatedAt
    0.43
     defendant
    0.42
     bogged
    0.42
    :"",
    0.41
    部は
    0.41
    POSITIVE LOGITS
    Lecture
    0.48
    ٓ
    0.43
    ٍ
    0.42
    ە
    0.41
    ൈ
    0.41
     هذا
    0.41
     क
    0.41
     आइ
    0.41
    Е
    0.41
    莒
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.